KVM: x86: fix singlestepping over syscall

commit c8401dda2f0a00cd25c0af6a95ed50e478d25de4 upstream.

TF is handled a bit differently for syscall and sysret, compared
to the other instructions: TF is checked after the instruction completes,
so that the OS can disable #DB at a syscall by adding TF to FMASK.
When the sysret is executed the #DB is taken "as if" the syscall insn
just completed.

KVM emulates syscall so that it can trap 32-bit syscall on Intel processors.
Fix the behavior, otherwise you could get #DB on a user stack which is not
nice.  This does not affect Linux guests, as they use an IST or task gate
for #DB.

This fixes CVE-2017-7518.

Cc: stable@vger.kernel.org
Reported-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
[bwh: Backported to 4.9:
 - kvm_vcpu_check_singlestep() sets some flags differently
 - Drop changes to kvm_skip_emulated_instruction()]
Cc: Ben Hutchings <benh@debian.org>
Cc: Salvatore Bonaccorso <carnil@debian.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 24 insertions, 30 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 19d14ac23ef9..fc3c7e49c8e4 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -296,6 +296,7 @@ struct x86_emulate_ctxt {
 
 	bool perm_ok; /* do not check permissions if true */
 	bool ud;	/* inject an #UD if host doesn't support insn */
+	bool tf;	/* TF value before instruction (after for syscall/sysret) */
 
 	bool have_exception;
 	struct x86_exception exception;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index de36660751b5..72b737b8c9d6 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2738,6 +2738,7 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 		ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
 	}
 
+	ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;
 	return X86EMUL_CONTINUE;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3dbcb09c19cf..595f8149c0d9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5250,6 +5250,8 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
 	ctxt->eflags = kvm_get_rflags(vcpu);
+	ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;
+
 	ctxt->eip = kvm_rip_read(vcpu);
 	ctxt->mode = (!is_protmode(vcpu))		? X86EMUL_MODE_REAL :
 		     (ctxt->eflags & X86_EFLAGS_VM)	? X86EMUL_MODE_VM86 :
@@ -5465,37 +5467,26 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 	return dr6;
 }
 
-static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r)
+static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
-	/*
-	 * rflags is the old, "raw" value of the flags.  The new value has
-	 * not been saved yet.
-	 *
-	 * This is correct even for TF set by the guest, because "the
-	 * processor will not generate this exception after the instruction
-	 * that sets the TF flag".
-	 */
-	if (unlikely(rflags & X86_EFLAGS_TF)) {
-		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-			kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 |
-						  DR6_RTM;
-			kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
-			kvm_run->debug.arch.exception = DB_VECTOR;
-			kvm_run->exit_reason = KVM_EXIT_DEBUG;
-			*r = EMULATE_USER_EXIT;
-		} else {
-			vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
-			/*
-			 * "Certain debug exceptions may clear bit 0-3.  The
-			 * remaining contents of the DR6 register are never
-			 * cleared by the processor".
-			 */
-			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
-			kvm_queue_exception(vcpu, DB_VECTOR);
-		}
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM;
+		kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
+		kvm_run->debug.arch.exception = DB_VECTOR;
+		kvm_run->exit_reason = KVM_EXIT_DEBUG;
+		*r = EMULATE_USER_EXIT;
+	} else {
+		vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
+		/*
+		 * "Certain debug exceptions may clear bit 0-3.  The
+		 * remaining contents of the DR6 register are never
+		 * cleared by the processor".
+		 */
+		vcpu->arch.dr6 &= ~15;
+		vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
+		kvm_queue_exception(vcpu, DB_VECTOR);
 	}
 }
 
@@ -5650,8 +5641,9 @@ restart:
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE)
-			kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+		if (r == EMULATE_DONE &&
+		    (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
 			__kvm_set_rflags(vcpu, ctxt->eflags);